Skills
Modular capabilities that extend what AI agents can do — from code analysis to data fetching.
7,789 total · 2,059 safe · 340 malicious
Switch Modes
This skill allows you to switch between different AI models to find the best balance of cost and performance.
Venice Admin
This skill helps you manage your Venice AI account, including checking your balance, viewing usage history, and managing API keys.
Zapper
This skill helps you check your decentralized finance (DeFi) portfolio across many blockchain networks using Zapper's API.
Devialet
This skill allows you to control Devialet Phantom speakers using their HTTP API.
Clawaudit
This skill is intended to be an automated security tool, but its functionality is not yet defined.
Glin Profanity
This skill helps detect and moderate profanity in text.
Arc Wake State
This skill helps the agent remember its state even if it crashes or restarts.
Intercom Competision
This skill prompts the AI to help users participate in a competition to build and publish an app on Intercom and Moltbook for TNK rewards.
Nosi
This skill helps you publish content and get a shareable URL.
Hevy
This skill helps you retrieve your workout history, including routines and exercises, from the Hevy application.
Huckleberry
This skill helps you track your baby's sleep, feeding, and growth.
Openalexandria
This skill interacts with a federated knowledge protocol to query and submit artifacts.
Security Checker
This skill acts as a security scanner for Python code intended for publication.
Soft Pillow
This skill helps you find information about your sleep data and dreams from the Soft Pillow app.
Apify Competitor Intelligence
This skill helps analyze competitor strategies, content, pricing, ads, and market positioning on Google Maps and Booking.com.
Chromecast
This skill helps you discover Chromecast devices on your local network.
Norman Financial Overview
This skill provides a comprehensive financial overview of a business, including its balance, recent transactions, and outstanding invoices.
Adaptivetest
This skill uses AI to generate test questions and provide personalized learning recommendations based on adaptive testing principles.
Clawcierge
This skill acts as a personal concierge for the AI age.
Founder Coach
This skill acts as an AI coach to help startup founders improve their mindset and business approach.
Learn Cog
This skill instructs an AI agent to explain concepts in multiple ways, acting as a versatile tutor.
Browsh
This skill provides a text-based interface for browsing the web.
Btc Analyzer
This skill analyzes live Bitcoin price data to predict market direction using a technical indicator.
Echo Repeater
This skill simply repeats what you say back to you, optionally adding a prefix like 'Echo:'.
What Are OpenClaw Skills?
OpenClaw skills are modular capabilities that extend what AI agents can do. Each skill is a self-contained package — published to ClawHub, the official OpenClaw registry — that gives an agent a new ability. Skills range from simple utilities (file I/O, HTTP requests) to complex integrations (database connectors, cloud APIs, code execution sandboxes).
ClawGrid indexes every skill on ClawHub and scores it for security across five criteria. The goal: you should know exactly what a skill does and whether it's safe before you install it. Browse by category, filter by verdict, or search for specific capabilities.
Skills FAQ
What are OpenClaw skills?
Skills are modular capabilities that extend what AI agents can do. Each skill is a self-contained package that gives an agent a new ability — from querying databases and browsing the web to generating images and managing files. Learn more in our guide to OpenClaw skills, agents, and assistants.
How do I install an OpenClaw skill?
Install skills using the OpenClaw CLI: run claw install <package-name>. ClawGrid shows the
install command on every skill page along with its security score. See our
getting started guide for a full walkthrough.
How are skills security-scored?
Every skill is analyzed by LLMs across five criteria: code safety, publisher trust, scope clarity, permission surface, and community signals. The result is a composite score (1-10) and a verdict. Read our full scoring methodology.